visdomloadshape: Smart Meter load shape data analysis tools for R

In ConvergenceDA/visdomloadshape: R package for load shape clustering and analysis, extending the visdom package

Description

Smart Meter load shape data analysis tools for R

Core functions

VISDOM load shape relies most heavily on the following core functions. See the example vignettes for examples of their usage:

• visdom: Depends lightly on the core visdom package functions, mainly the ability for a data source to return data in the appropriate format.

• create_dictionary: Starting with raw load data, create a dictionary of cluster centers and return encodings in one shot.

• dictionary.distance: Compare two load shape dictionaries.

• draw.top.n.shapes: Given a set of encodings and their corresponding dictionary, plot the top load shapes present.

• encode: Given raw meter data and a target dictionary, encode each load day worth of data with its best fit cluster assignment.

• impute: Impute meter data to eliminate blanks (necessary for clustering algorithm to function).

• quick.norm: Efficiently normalize each day of load data for use in a k-mean family algorithm.

• raw2encoded: Starting with raw meter data, cluster into a dictionary of best fit load shapes and perform encoding with that dictionary.

• reduce.dictionary: Shrink a dictionary by merging the most similar entries with each other.

• shannon.entropy: Information entropy calculation on a table of load shape encoding counts.

• shannon.entropy2: Information entropy calculation on load shape encodings.

ConvergenceDA/visdomloadshape documentation built on May 8, 2019, 8:34 a.m.